<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
rubert-tiny2_finetuned_emotion_experiment_augmented_anger_fear_no_emojis
This model is a fine-tuned version of cointegrated/rubert-tiny2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5820
- Accuracy: 0.7881
- F1: 0.7886
- Precision: 0.7906
- Recall: 0.7881
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.0996 | 1.0 | 69 | 1.0013 | 0.6879 | 0.6779 | 0.7070 | 0.6879 |
| 0.9524 | 2.0 | 138 | 0.8651 | 0.7265 | 0.7245 | 0.7322 | 0.7265 |
| 0.8345 | 3.0 | 207 | 0.7821 | 0.7422 | 0.7413 | 0.7445 | 0.7422 |
| 0.7573 | 4.0 | 276 | 0.7222 | 0.7484 | 0.7473 | 0.7482 | 0.7484 |
| 0.6923 | 5.0 | 345 | 0.6828 | 0.7568 | 0.7562 | 0.7562 | 0.7568 |
| 0.6412 | 6.0 | 414 | 0.6531 | 0.7568 | 0.7559 | 0.7556 | 0.7568 |
| 0.5982 | 7.0 | 483 | 0.6320 | 0.7610 | 0.7601 | 0.7597 | 0.7610 |
| 0.5593 | 8.0 | 552 | 0.6133 | 0.7651 | 0.7655 | 0.7664 | 0.7651 |
| 0.5183 | 9.0 | 621 | 0.6036 | 0.7714 | 0.7708 | 0.7709 | 0.7714 |
| 0.5042 | 10.0 | 690 | 0.5951 | 0.7756 | 0.7755 | 0.7760 | 0.7756 |
| 0.483 | 11.0 | 759 | 0.5878 | 0.7766 | 0.7768 | 0.7774 | 0.7766 |
| 0.4531 | 12.0 | 828 | 0.5855 | 0.7850 | 0.7841 | 0.7839 | 0.7850 |
| 0.4386 | 13.0 | 897 | 0.5828 | 0.7797 | 0.7790 | 0.7786 | 0.7797 |
| 0.4238 | 14.0 | 966 | 0.5788 | 0.7777 | 0.7780 | 0.7786 | 0.7777 |
| 0.4018 | 15.0 | 1035 | 0.5793 | 0.7839 | 0.7842 | 0.7855 | 0.7839 |
| 0.3998 | 16.0 | 1104 | 0.5801 | 0.7850 | 0.7844 | 0.7841 | 0.7850 |
| 0.3747 | 17.0 | 1173 | 0.5791 | 0.7839 | 0.7836 | 0.7833 | 0.7839 |
| 0.3595 | 18.0 | 1242 | 0.5799 | 0.7891 | 0.7891 | 0.7894 | 0.7891 |
| 0.3575 | 19.0 | 1311 | 0.5820 | 0.7881 | 0.7886 | 0.7906 | 0.7881 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
